IonToParquet

id: ion_to_parquet
namespace: company.team

tasks:
  - id: download_csv
    type: io.kestra.plugin.core.http.Download
    description: salaries of data professionals from 2020 to 2023 (source ai-jobs.net)
    uri: https://huggingface.co/datasets/kestra/datasets/raw/main/csv/salaries.csv

  - id: avg_salary_by_job_title
    type: io.kestra.plugin.jdbc.duckdb.Query
    inputFiles:
      data.csv: "{{ outputs.download_csv.uri }}"
    sql: |
      SELECT
        job_title,
        ROUND(AVG(salary),2) AS avg_salary
      FROM read_csv_auto('{{ workingDir }}/data.csv', header=True)
      GROUP BY job_title
      HAVING COUNT(job_title) > 10
      ORDER BY avg_salary DESC;
    store: true

  - id: result
    type: io.kestra.plugin.serdes.parquet.IonToParquet
    from: "{{ outputs.avg_salary_by_job_title.uri }}"
    schema: |
      {
        "type": "record",
        "name": "Salary",
        "namespace": "com.example.salary",
        "fields": [
          {"name": "job_title", "type": "string"},
          {"name": "avg_salary", "type": "double"}
        ]
      }